Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal capability and skill levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agos
    -0.17
    onta
    -0.15
    ober
    -0.15
    ære
    -0.15
    geom
    -0.15
    ãĥŃãĥ³
    -0.15
    gia
    -0.15
    psz
    -0.14
    enheim
    -0.14
    idenav
    -0.14
    POSITIVE LOGITS
     skills
    0.40
    skills
    0.34
     skill
    0.33
     Skills
    0.32
    Skills
    0.30
     abilities
    0.28
     skilled
    0.28
    æĬĢèĥ½
    0.26
     Skill
    0.26
    skill
    0.26
    Act Density 0.302%

    No Known Activations